Application of SVM and ANN for image retrieval |
| |
| Affiliation: | 1. Department of Radiology, Zhongshan Hospital, Fudan University and Shanghai Medical Imaging, Institute, Shanghai 200032, People''s Republic of China;2. Department of Medical Imaging, Shanghai Medical School of Fudan University, Shanghai, 200032, People''s Republic of China;3. Department of radiology, The first affiliated hospital of Fujian Medical University, Fuzhou, 350005, People''s Republic of China;4. Department of Pathology, Zhongshan Hospital, Fudan University, Shanghai 200032, People''s Republic of China |
| |
| Abstract: | This paper presents a new, scaling and rotation invariant encoding scheme for shapes. Support vector machines (SVMs) and artificial neural networks (ANNs) are used for the classifications of shapes encoded by the new method. The SVM classification accuracy rate is 95.9 ∓ 2.9% in 14 categories and 79.2 ∓ 2.1% in 40 categories. This shows that SVM is one of the best tools for classification problems. The experimental results showed that SVM achieved better performance than ANN. A sensitivity test is performed to show that SVM is quite robust against different parameter values. In addition, our coding method is comparable to previous coding scheme in terms of SVM and ANN performance. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
